Fetching from the wire…
OSS2026-07-30 · source-backed
Intuition-Lab/personal-model (created July 10, 1,263 stars, v0.3.2) is a local-first long-term memory runtime that learns how you work from focused activity captured on macOS after you grant permission, then serves it to Claude Code, Codex, and Cursor Agent over MCP as a single evidence-linked HUMAN.md. Registered in the official MCP registry. The structural claim, Points/Lines/Faces/Volumes and a Root each traceable to captured evidence and individually inspectable, correctable, exportable, and deletable, is a sharper answer to the memory-provenance problem than opaque embedding stores. Whether you want continuous activity capture is a separate question with a real answer either way.
Each link below shares sources, entities, or timing with this story.
diegosouzapw/OmniRoute added 1,343 stars on July 20, a single MIT-licensed gateway across 268+ providers (50+ free) and 500+ models including Claude, GPT, Gemini, Kimi K3, GLM and DeepSeek, wired for Claude Code, Codex, Cursor, Cline and Copilot. Quota-aware automatic fallback...
QM went up under MIT license. Created July 29. As of the GitHub API check: 8,420 stars, 887 forks. Five days. YC uses it internally across accounting, legal, events, and engineering, including to build QM itself. Every employee and every Slack room gets its own scoped memory,...
Twenty themes, 57 "slop-test" gates, four verbs (build, audit, redesign, study), targeting Claude Code, Cursor, and Codex. It hit #2 on GitHub Trending July 15 and reached 11.1K stars by July 17. This is the first widely adopted artifact treating taste as an installable, gate-...
A local-first observability dashboard that tails agent session files to show plans, tool calls, file changes and progress in real time across three different coding agents, MIT-licensed, still being pushed today (GitHub). It's the only repo carrying the agent-observability top...
The agent-security topic holds 42 repos above 100 stars, four from large companies rather than startups: NVIDIA/SkillSpector (14,498 stars, scanning Claude Code/Codex/MCP skills for prompt injection), Tencent/AI-Infra-Guard (4,467, red-teaming with Many-Shot/PAIR/GOAT/ActorAtt...
Everyone writing SKILL.md files has absorbed the same folklore. Keep the top file thin. Push detail into reference files. Let the agent walk the tree as needed. More layers, more context efficiency. A controlled study submitted July 20 tested that across InfiniteBench, three a...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.